This account will eventually be for Peace Village😅 for now I'm studying crypto currency stuff and linking posts of interest... None of this is financial advice! 👌

🚨ESTO ACABA DE MATAR A ELEVENLABS 74.000 personas ya lo han guardado en GitHub y casi nadie habla de ello. Se llama VoiceStudio y es un reemplazo 100% gratis que corre en tu propio ordenador. Te permite: → Clonar tu propia voz → Doblar vídeos a 646 idiomas → Crear audiolibros y dictar → Elegir entre 17 motores Sin pago por carácter. Sin límites de uso. Todo en tu máquina. 🔖 Guárdalo.

NVIDIA just released Kimodo, a controllable human motion diffusion model, on Hugging Face It turns text and kinematic constraints into high-quality 3D human and robot motion, trained on 700 hours of mocap data.

GitHub is a GOLDMINE for AI game developers. I picked 10 powerful open-source repos that make building 3D games with Claude Code and Codex ridiculously easier. Save these before your next project: 1. Gamedev Agent Skills Give Claude Code and Codex reusable game-development skills for engines including Godot, Unity, Unreal, and Three.js. github.com/gamedev-skills/aw… 2. MCP Unity Connect your coding agent to Unity. Create scenes, modify objects, assign materials, run tests, and read console errors through prompts. github.com/CoderGamester/mcp… 3. Godot MCP Let your AI assistant create scenes, add nodes, run Godot projects, and inspect debug output while building your game. github.com/Coding-Solo/godot… 4. TripoSR Turn a single image into a 3D model. Useful for prototyping props and exploring assets before refining them for your game. github.com/VAST-AI-Research/… 5. Drei Ready-made helpers for React Three Fiber: camera controls, environments, skies, shadows, and model loading for browser-based 3D games. github.com/pmndrs/drei 6. React Three Rapier Add physics to React Three Fiber games, including rigid bodies, collision detection, and joints, without writing a physics engine yourself. github.com/pmndrs/react-thre… 7. Yuka Build NPC behavior with steering, pathfinding, perception, and state-driven decisions. Give your characters more to do than stand around. github.com/Mugen87/yuka 8. Three.quarks Build particle effects for Three.js games, from sparks and smoke to magical trails. Includes a visual editor for designing effects. github.com/Alchemist0823/thr… 9. React Postprocessing Give React Three Fiber scenes a visual upgrade with bloom, depth of field, noise, and vignette effects. github.com/pmndrs/react-post… 10. Colyseus Build multiplayer features with rooms, matchmaking, reconnections, and automatic game-state synchronization between your server and players. github.com/colyseus/colyseus Which one are you using in your next game?

NVIDIA ACABA DE SACAR UNA HERRAMIENTA PARA CONVERTIR CUALQUIER IMAGEN EN UN MUNDO 3D EXPLORABLE y la han hecho 100% de código abierto. → modelo disponible en hugging face → código de la interfaz disponible en GitHub Lyra 2.0 crea un mundo por el que puedes caminar, girar y hasta soltar un robot para simulación. os dejo el repo abajo.

🚨 A Netflix engineer just open-sourced the fix for the most expensive problem in AI: wasted tokens It's called Headroom, and it might be the smartest fix to high token usage Your agent reads a 10,000-token log file to find one error. You paid for all 10,000 tokens. The answer needed 1,200. Headroom sits between your agent and the LLM and compresses everything before the model sees it. JSON, code, logs, RAG chunks, each gets its own specialized compressor. And it's reversible: the originals stay on your machine, so nothing is lost. The results speak for themselves: → Up to 95% fewer tokens → Same accuracy on benchmarks → Zero changes to your code Setup takes one minute: 1. pip install "headroom-ai[all]" 2. headroom wrap claude Done. Works with Claude Code, Cursor, Codex, and anything OpenAI-compatible. Everything runs locally, fully open source. The cheapest token is the one you never send. 🔗 Github repo: github.com/headroomlabs-ai/h… So, are you compressing your context, or just paying the bill?

✍️

You don't need a multi-camera studio setup, expensive suits, or cloud subscription software to do performance motion capture anymore. A single video file inside Blender is all it takes. Arcomade just released BlendCap—a 100% local, offline Blender add-on that extracts full-body, hand, and facial tracking directly from video footage. It maps performance straight onto Rigify, Auto-Rig Pro, Mixamo, or CloudRig setups and includes instant FK-to-IK conversion for fast keyframe cleanup. For solo animators and indie game devs: would you use video mocap for primary animation, or just for blocking out initial poses? #b3d #mocap #indiegamedev

Disney cartoon designers accidentally leaked this motion video repos and its f*ckin crazy They are building this with Jev. A tiny AI model that doesn’t write. It just picks the right component in milliseconds. 4 repos to steal from: > Shapeshift - one input that morphs into the right UI as you type: event card, checklist, timer, color picker, poll. One Jev call answers 14 questions in parallel. Runs offline without an account bun install && bun dev -> github.com/anishfn/shapeshif… > json-render by Vercel Labs - generative UI from your own component catalog. Its experimental Jev mode picks which components and actions the screen should contain Try it: json-render.dev/playground -> "Jev (Experimental)" -> github.com/vercel-labs/json-… > unclutter by Kitze - a browser extension where Jev decides element by element what's clutter and wipes it off the page -> github.com/kitze/unclutter > jev-canvas - draw on a tldraw canvas with your voice and a pointing finger. Jev decides the action, the target and where it goes -> github.com/gaborishka/jev-ca… Here's why it works: Jev never generates your UI. It only chooses from components you already built. Your design system stays intact, and the model can't hallucinate a broken button. The designer's job is shifting from drawing every screen to building the pieces and letting the interface pick. More Jev projects: github.com/yibie/awesome-jev Save this for your next redesign.

🤯 کلاد اپوس 5.5 ظاهراً Three.js رو به یه سطح دیگه برده! یه نقشه ساختمون رو بهش می‌دی و در نهایت یه خونه سه‌بعدی تحویلت می‌ده که می‌تونی توش قدم بزنی؛ حتی قبل از اینکه ساخته شده باشه! 🏠🔥 جالبه بدونی سازنده‌های خونه برای چنین مدل‌هایی به‌ازای هر نقشه بین ۵ تا ۱۰ هزار دلار هزینه می‌کنن تا مشتری بتونه قبل از ساخت، خونه رو مجازی ببینه و تغییرات دلخواهش رو اعمال کنه. اما بخش جذاب ماجرا اینجاست که می‌شه کل فرایند جذب مشتری رو با AI اتوماتیک کرد: 🔹 پیدا کردن سازنده‌هایی که برای نقشه‌هاشون مدل سه‌بعدی ندارن 🔹 دادن نقشه و عکس‌های خونه به Opus 5.5 🔹 ساخت یه سایت سه‌بعدی مقیاس‌دار و قابل قدم زدن 🔹 فرستادن نسخه آماده برای سازنده، قبل از اینکه حتی پیشنهادی بهش بدی! 🔹 گرفتن پروژه برای تبدیل کل کاتالوگ نقشه‌هاش به مدل سه‌بعدی و با هر نقشه جدیدی که منتشر می‌کنه، دوباره همین فرایند رو اجرا کنی! حتی می‌تونی چند ایجنت بسازی که یکی خونه رو طراحی کنه و اون یکی تصاویرش رو با عکس‌های واقعی مقایسه کنه؛ بعد این چرخه بارها تکرار بشه تا نتیجه بهتر بشه. 🤯 پرامپت شروع کار هم آماده‌ست: «این نقشه و عکس‌های یک خونه رو بگیر و با Three.js یه سایت سه‌بعدی بساز که بتونم داخلش قدم بزنم. ابعاد رو دقیقاً مطابق نقشه پیاده کن و اتاق‌ها، متریال‌ها و مبلمان رو تا جای ممکن با عکس‌ها مطابقت بده. خونه رو به بخش‌های جدا تقسیم کن و برای هر بخش یک ایجنت سازنده و یک منتقد مستقل در نظر بگیر. منتقد باید تصویر خروجی هر اتاق رو با عکس واقعی مقایسه کنه، بهترین نسخه رو انتخاب کنه، بزرگ‌ترین تفاوت رو مشخص کنه و برای اصلاح به سازنده برگردونه. این چرخه رو ادامه بده تا خروجی بهتر بشه یا من متوقفش کنم. در پایان هم بگو کدوم جزئیات رو نتونستی دقیقاً بازسازی کنی.» تصور کن یه ایجنت بتونه با همین روش، برای ده‌ها پروژه ساختمونی مدل سه‌بعدی بسازه و هر بار قبل از فروش، نمونه کار اختصاصی مشتری رو آماده کنه! 🚀

兄弟们，看了一圈 Gemini 4 Argon 在2D转3D方面确实遥遥领先。别再以为搞 3D 必须开 Blender 熬夜雕面调骨骼了。 看看原推这玩意儿，直接把我给看清醒了： 给模型一张 2D 维多利亚马车图，零人工参与，纯靠代码直接吐出了一个完整的 WebGL 交互级 3D 资产！扒了一下原推的关键实测数据，极其哈人： 1. 纯代码暴力建构：整整 17.4 万面（Face），没动哪怕一秒 Blender，全是程序化几何直接生成； 2. 带复杂物理装配：不是死模型！车门能开合、车窗带铰链、车轮自带真实的悬挂与回弹物理； 3. 高阶细节与着色：车头的提灯自带动态烛光闪烁，甚至车身上还雕刻了完整的立体骷髅浮雕。大部分人以为大模型只会写两行前端页面或者生成 2D 废话。 真正的技术降维是：大模型正在把图形学渲染管线和几何拓扑当成底层指令直接编译。独立开发者以后做 3D 网页展厅、轻量小游戏，生产力直接被暴力拉平几百倍。 懂 Three.js 和 WebGL 渲染管线的兄弟帮掌掌眼，这种代码生成的拓扑放移动端能扛住几帧？👇 x.com/thebuggeddev/status/21…

Two Anthropic engineers built a prompt system that spits out a rigged Blender monster in minutes, and the trick is that it never designs the creature It designs the skeleton first. Anatomy decides what a creature can do, and everything strange gets added on top of something that works. > FRAME - limb count, joint positions and weight distribution set before any mesh exists > FLESH - muscle volumes grown onto that frame, so the silhouette follows the structure > WARP - the strangeness applied last, as deformation rather than invention Image-led creature generation looks incredible and falls apart on the rig. Limbs bend in places nothing could bend. Starting from a skeleton flips the failure. The monster may look wrong on purpose, but it always moves like something alive. The warp stage is where the personality arrives. Stretch one limb pair, collapse a joint, invert a spine curve, and it reads as a different species. Because the frame is parametric, every variant is one number away. A hundred monsters cost barely more than the first. Weight distribution is the detail everyone skips. It decides posture, and posture is what makes a creature look dangerous or sick. Studios build this knowledge into one senior artist. Here it sits in a prompt that any junior can run. The full prompt chain and a batch of monsters from one frame are laid out underneath.

If you're a designer, freelancer, founder or frontend developer, bookmark this. 1. scrolltide.co - 600+ award-winning prompts with full source code for 3D and scroll-driven sites (for all of you) 2. godly.website - hand-picked websites with serious craft 3. mobbin.com - real app UI screens 4. styles.refero.design - real product design styles 5. awwwards.com - the sites that actually won 6. shadcnblocks.com - full blocks, not just buttons 7. v0.dev - prompt to UI, from Vercel 8. supahero.io - hero sections worth stealing 9. ui.aceternity.com - animated components, big visual impact 10. threejs-journey.com - the best way to learn 3D on the web What did I miss?

github.com/MaxLiu22/Motion2M… Made an open-source one that does the same thing, and there's a Blender extension available for it now too.

LO QUE ESTE TIPO SUBIÓ A GITHUB NO DEBERÍA SER GRATIS una app que convierte tu móvil en un detector de vigilancia. escucha las señales Wi-Fi y Bluetooth a tu alrededor y te dice qué hay cerca: → rastreadores escondidos → cámaras corporales de policía → drones, y dónde está el piloto → gafas inteligentes de Meta grabando → micrófonos de detección de disparos reconoce hasta 242 tipos de dispositivos. y te avisa si alguno se mueve contigo. sin cuenta. sin servidor. sin internet. código abierto. os dejo el repo abajo.

The weekly update on the #Altcoin portfolio. It's currently at $180,000. At the start of August, it was just $75,000. I'm currently 85% allocated into the markets, as I do continue to expect to see a strong move in the coming period on #Altcoins. My largest allocations are: - $EIGEN - $W - $PLUME - $TAO It's a great mix of Ethereum ecosystem, Solana ecosystem, RWA and AI. I've scaled down my positions into $NEAR and $GRASS (the last one was fully closed for a 120% gain in less than two weeks). I've added in the recent correction into $PLUME and $EIGEN. I'm planning to be writing weekly updates, but if you're looking for real-time updates with all of my trades (sells and buys) and educational content + extra daytrades, join me here: x.com/CryptoMichNL/creator-s…

ESTO ES JODIDAMENTE INCREÍBLE un dev en solitario acaba de abrir el código de un reemplazo 100% GRATIS de ElevenLabs que se ejecuta completamente en tu propia máquina. el repo de GitHub está en 19.4K estrellas. te permite: → clonar una voz desde un clip de referencia limpio → doblar cualquier video a 646 idiomas → generar audiolibros, dictado, transcripción → elegir entre 14 motores TTS en lugar de uno ElevenLabs soporta 32 idiomas. esto hace 646. sin cobro por carácter. sin límites de uso. ningún audio sale nunca de tu computadora. guarda esto para después. os dejo el repo abajo

🚨Architects are going to hate this. Someone just open-sourced a full 3D building editor that runs entirely in your browser. No AutoCAD. No Revit. No $5,000/year licenses. It's called Pascal Editor. Built with React Three Fiber and WebGPU -- meaning it renders directly on your GPU at near-native speed. Here's what's inside this thing: → A full building/level/wall/zone hierarchy you can edit in real time → An ECS-style architecture where every object updates through GPU-powered systems → Zustand state management with full undo/redo built in → Next.js frontend so it deploys as a web app, not a desktop install → Dirty node tracking -- only re-renders what changed, not the whole scene Here's the wildest part: You can stack, explode, or solo individual building levels. Select a zone, drag a wall, reshape a slab -- all in 3D, all in the browser. Architecture firms pay $50K+ per seat for BIM software that does this workflow. This is free. 100% Open Source.

These are the fastest-growing public Claude skills. They will literally 10x your productivity. I turned the repos into prompts so you can install them all instantly. 🧵: 8 Claude skills worth installing (prompts attached). 👇

Real human voice cloning just crossed the uncanny valley. You can now clone voices that sound actually full real human, Not robotic, A Open-source 1.7B model Clone any voice in seconds. Emotions, age, tone, personality & accent all controllable. Low latency, Multilingual. - huggingface.co/Qwen/Qwen3-TT…

Every vibe coder's pre-launch prompt: "Claude, before I launch, do these 20 things: 1. Hide every API key. Nothing in the frontend, nothing in git 2. Rotate any key that was ever committed 3. Turn on rate limiting so one user can't burn my bill 4. Check auth on every route not just the UI 5. Lock down database rules so users only see their own data 6. Validate every input on the server 7. Add a spending cap on my AI provider 8. Make sure errors don't leak stack traces 9. Set up error tracking so I know before users tweet 10. Back up the database and actually test a restore 11. Add a 404 and a 500 page that don't look broken 12. Make it work on a cheap Android phone 13. Fix anything that takes more than 3 seconds to load 14. Add meta tags + OG image so links look good on X 15. Add privacy policy + terms (yes, really) 16. Set up analytics so I know where people drop off 17. Test signup, payment and password reset end to end 18. Make sure emails don't land in spam 19. Add a way for users to contact me 20. Write a rollback plan in case launch day goes wrong Make no mistakes." Funny thing is, this is genuinely the whole checklist. Bookmark this + send it to a friend launching this week.